#! /usr/bin/env guile !# (use-modules (rnrs programs) (rnrs io ports) (srfi srfi-1) (srfi srfi-26) (ice-9 getopt-long) (ice-9 match) (ice-9 regex) (transform strings) (transform sql) (transform triples) (transform special-forms)) (define-transformer genotypes (tables (Geno (left-join Species "USING (SpeciesId)"))) (schema-triples (gnt:chr a owl:ObjectProperty) (gnt:chr skos:description "This resource is located on a given chromosome") (gnt:chr rdfs:domain gnc:Genotype) (gnt:mb a owl:ObjectProperty) (gnt:mb skos:definition "The size of this resource in Mb") (gnt:mb rdfs:domain gnc:Genotype) (gnt:mbMm8 a owl:ObjectProperty) (gnt:mbMm8 skos:definition "TODO") (gnt:mbMm8 rdfs:domain gnc:Genotype) (gnt:mb2016 a owl:ObjectProperty) (gnt:mb2016 skos:definition "TODO") (gnt:mb2016 rdfs:domain gnc:Genotype) (gnt:hasSequence a owl:ObjectProperty) (gnt:hasSequence skos:definition "This resource has a given sequence") (gnt:hasSequence rdfs:domain gnc:Genotype) (gnt:hasSource a owl:ObjectProperty) (gnt:hasSource rdfs:domain gnc:Genotype) (gnt:hasSource skos:definition "This resource was obtained from this given source") (gnt:hasAltSourceName a owl:ObjectProperty) (gnt:hasAltSourceName rdfs:domain gnc:Genotype) (gnt:hasAltSourceName skos:definition "The alternative name this resource was obtained from") (gnt:chrNum a owl:ObjectProperty) (gnt:chrNum rdfs:domain gnc:Genotype) (gnt:chrNum skos:definition "The chromosome number for this resource")) (triples (string->identifier "" (regexp-substitute/global #f "[^A-Za-z0-9:]" (field Geno Name) 'pre "_" 'post) #:separator "" #:proc string-capitalize-first) (set rdf:type 'gnc:Genotype) (set rdfs:label (sanitize-rdf-string (field Geno Name))) (set gnt:chr (field Geno Chr)) (set gnt:mb (annotate-field (field ("IFNULL(Geno.Mb, '')" Mb)) '^^xsd:double)) (set gnt:mbMm8 (annotate-field (field ("IFNULL(Geno.Mb_mm8, '')" Mb_mm8)) '^^xsd:double)) (set gnt:mb2016 (annotate-field (field ("IFNULL(Geno.Mb_2016, '')" Mb_2016)) '^^xsd:double)) (set gnt:hasSequence (field Geno Sequence)) (set gnt:hasSource (field Geno Source)) ;; Only transform Source2 if it differs from Source (set gnt:hasAltSourceName (field ("IF((Source2 = Source), NULL, Source2)" Source2))) (set gnt:belongsToSpecies (string->identifier "" (remap-species-identifiers (field Species Fullname)) #:separator "" #:proc string-capitalize-first)) (set gnt:chrNum (annotate-field (field Geno chr_num) '^^xsd:int)) (set rdfs:comments (field Geno Comments)))) (let* ((option-spec '((settings (single-char #\s) (value #t)) (output (single-char #\o) (value #t)) (documentation (single-char #\d) (value #t)))) (options (getopt-long (command-line) option-spec)) (settings (option-ref options 'settings #f)) (output (option-ref options 'output #f)) (documentation (option-ref options 'documentation #f)) (%connection-settings (call-with-input-file settings read))) (with-documentation (name "Genotype Metadata") (connection %connection-settings) (table-metadata? #f) (prefixes '(("dct:" "<http://purl.org/dc/terms/>") ("gn:" "<http://genenetwork.org/id/>") ("gnc:" "<http://genenetwork.org/category/>") ("gnt:" "<http://genenetwork.org/term/>") ("rdf:" "<http://www.w3.org/1999/02/22-rdf-syntax-ns#>") ("rdfs:" "<http://www.w3.org/2000/01/rdf-schema#>") ("owl:" "<http://www.w3.org/2002/07/owl#>") ("skos:" "<http://www.w3.org/2004/02/skos/core#>") ("xkos:" "<http://rdf-vocabulary.ddialliance.org/xkos#>") ("xsd:" "<http://www.w3.org/2001/XMLSchema#>"))) (inputs (list genotypes)) (outputs `(#:documentation ,documentation #:rdf ,output))))